Using graph queries to obtain results from machine learning models

This invention describes a system where you can ask a graph database a question, called a "graph query." This query tells the system what information to feed into a trained artificial intelligence model. The AI model then processes this information and creates new data, which the graph database uses to help answer your original question, essentially having the AI dynamically build or enhance parts of the graph structure to give you results.

Why it matters: Filed before the widespread adoption and capabilities of generative AI models. The claims describe an ML model generating parts of a graph data structure, a task now significantly enhanced by more powerful and accessible generative AI.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedGraph database, machine learning models, software integration

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10